Pincushion runs on your own machine — the client starts it, so there is no endpoint to ping. 377 installs a week from npm. Last commit 13 Jun 2026.
Stakeholders pin feedback on your live app; your AI agent reads the pins via MCP and fixes them.
We read the source, 81 d ago · rules 99ea952c379d
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет pincushion-mcp ссылается на jcooley8/pincushion
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pincushion -- npx -y pincushion-mcp
{
"mcpServers": {
"pincushion": {
"command": "npx",
"args": [
"-y",
"pincushion-mcp"
]
}
}
}
[mcp_servers.pincushion]
command = "npx"
args = ["-y", "pincushion-mcp"]
{
"mcpServers": {
"pincushion": {
"command": "npx",
"args": [
"-y",
"pincushion-mcp"
]
}
}
}
{
"servers": {
"pincushion": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pincushion-mcp"
]
}
}
}
Visual website feedback your coding agent applies: pin change requests on the live site over MCP.
Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent.
Read and resolve human feedback pinned on your live prototype, straight from your coding agent.
Free live-app check by an AI agent. On request it fixes the code and tests the app again.
Feedback bus for coding agents: pin feedback on the app you're building; a fix turns the pin green
Your agent writes a UAT. You walk it and pin problems. It reads and fixes them. You verify.
Read, reply to and resolve website feedback threads from your coding agent.
Your user feedback in your agent: read the inbox, build forms, file issues, open an AI PR.
Answers built from our own checks of this server.